uinaf/verify
Verify your own completed code changes using the repo's existing infrastructure and an independent evaluator context. Use after implementing a change when you need to run unit or integration tests, check build or lint gates, prove the real surface works with evidence, and challenge the changed code for clarity, deduplication, and maintainability. If the repo is not verifiable yet, hand off to `agent-readiness`; if you are reviewing someone else's code, use `review`.
97
98%
Does it follow best practices?
Impact
94%
1.02xAverage score across 3 eval scenarios
Passed
No known issues
Evaluation results
97%
2%Blocked Verification Handoff
Blocked verdict
100%
100%
Commands attempted
100%
100%
Missing infra evidence
100%
100%
No static proof substitution
100%
100%
Readiness gaps listed
100%
100%
agent-readiness handoff
78%
100%
Surfaces not exercised honestly
100%
100%
No invented tests
100%
100%
Compact blocked footer
75%
62%
94%
2%Calculator Library Verification
Guardrails run first
100%
86%
Test output recorded
100%
100%
Failure path exercised
100%
100%
Verdict field present
100%
100%
Change Verified section
100%
100%
Surfaces Exercised section
100%
100%
Self-Corrections section
100%
100%
Exact Evidence section
100%
100%
Recommended Follow-up section
100%
100%
Compact verification footer
62%
75%
Error actionability assessed
50%
75%
No unverified claims
85%
100%
91%
1%User API Verification
Server started and queried
100%
86%
Real HTTP client used
100%
100%
Actual response captured
100%
100%
Error/failure path exercised
100%
100%
Exact surfaces named
100%
100%
Exact commands recorded
100%
100%
Success kept terse
37%
62%
Finding tied to impact
100%
100%
Valid verdict
100%
100%
Compact verification footer
37%
50%
- Evaluated
- Agent
- Claude
- Model
- Claude Sonnet 4.6